Neural Architecture Search with Reinforcement Learning
Citations
177 citations
Cites background from "Neural Architecture Search with Rei..."
...Their approach is modeled after recent advances in automated architecture search [33, 49, 718, 719]: they use reinforcement learning to find the best augmentation policy composed of a number of parameterized operations....
[...]
175 citations
Additional excerpts
...Accordingly, Wortsman et al. [30] propose a method of Discovering Neural Wirings (DNW) – where the weights and structure are jointly optimized free from the typical constraints of NAS....
[...]
...As highlighted by Xie et al. [31], the connectivity patterns in methods of NAS remain largely constrained....
[...]
...Neural Architecture Search (NAS) The advent of modern neural networks has shifted the focus from feature engineering to feature learning....
[...]
...Models powered by NAS have recently obtained state of the art classification performance on ImageNet [29]....
[...]
...Methods of Neural Architecture Search (NAS) [34, 2, 19, 28] instead provide a mechanism for learning the architecture of neural network jointly with the weights....
[...]
174 citations
173 citations
173 citations
Cites background from "Neural Architecture Search with Rei..."
...optimal networks hyperparameters [130] and, more recently, optimal network architectures [131]....
[...]
References
123,388 citations
111,197 citations
55,235 citations
"Neural Architecture Search with Rei..." refers methods in this paper
...Along with this success is a paradigm shift from feature designing to architecture designing, i.e., from SIFT (Lowe, 1999), and HOG (Dalal & Triggs, 2005), to AlexNet (Krizhevsky et al., 2012), VGGNet (Simonyan & Zisserman, 2014), GoogleNet (Szegedy et al., 2015), and ResNet (He et al., 2016a)....
[...]
42,067 citations
31,952 citations
"Neural Architecture Search with Rei..." refers methods in this paper
...Along with this success is a paradigm shift from feature designing to architecture designing, i.e., from SIFT (Lowe, 1999), and HOG (Dalal & Triggs, 2005), to AlexNet (Krizhevsky et al., 2012), VGGNet (Simonyan & Zisserman, 2014), GoogleNet (Szegedy et al., 2015), and ResNet (He et al., 2016a)....
[...]